Zearch MCP
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP port when `--port` isn't given. | 8787 |
| ZEARCH_UI | No | `0` turns off the inline answer view. | on |
| ZEARCH_API_KEY | Yes | Your Zearch API key. In HTTP mode, callers send their own key. | |
| ZEARCH_API_URL | No | API base URL. `http://` is accepted only for localhost. | https://zearch.computer/v1 |
| ZEARCH_TIMEOUT_MS | No | Per-request timeout. Research streams get at least 180 s. | 120000 |
| ZEARCH_REVERSE_WAIT_MS | No | How long `research` waits for a `reverse` run before returning its id for `get_run`. | 300000 |
| ZEARCH_MCP_ALLOWED_HOSTS | No | Same as `--allowed-hosts`. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Zearch is a research engine that checks every paragraph against its sources before returning it.
Use research for questions about the world that need current or cited facts. Each answer comes with numbered sources, the exact passage Zearch's evidence model (Jev) read, and a per-paragraph support score. When Zearch can't support an answer it returns the best source passage instead (answer_type "excerpt"); present that as a quote, not as a conclusion.
Use verify to check text you or another model wrote against sources you already have, before showing it to someone.
When you pass on a Zearch answer, keep the [n] citations next to the claims they support and list the sources. Don't add claims the sources don't make. Research and verification spend the user's Zearch credits; errors are free.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| researchA | Ask Zearch a question. Zearch searches the web (or reads the page or site you give it), Jev selects the passages that answer it, a writer drafts from those passages only, and Jev checks every paragraph against its cited source before the answer is returned. Unsupported paragraphs are cut; if nothing survives you get the selected source passage (answer_type "excerpt"). Modes and credits: standard (1, a direct answer in seconds), deep (5, a cited report from up to 8 sources), compare (2, a side-by-side comparison), scrape (1, what one public HTTPS page says; needs url), crawl (3, up to five pages of one site; needs url), reverse (10, static analysis of how an app, repo or site works; needs url, runs on a queue and can take minutes). A follow-up with parent_id that needs no new search costs 0.3. Errors are free. Returns the answer as Markdown with [n] citations, the sources with the exact excerpt Jev read, per-paragraph support scores, and suggested follow-ups. |
| verifyA | Check text against the sources it cites, paragraph by paragraph, with Jev (the same check Zearch runs on its own answers). Cite sources inline as [1], [2]… in the order you list them. Use it to gate output from your own model before a person sees it. Limits: text up to 8,000 characters; 1 to 8 sources of up to 20,000 characters each. Costs 1 credit, charged only when the check completes. Returns pass/fail per paragraph with support and attribution probabilities. |
| get_runA | Fetch one of your Zearch runs by id: its answer, sources, verification and status. Use it to check on a queued Reverse engineer run, or to reopen an earlier answer. Free. |
| list_runsA | List your recent Zearch runs, newest first. The app and the API share one history. Free. Page with starting_after. |
| get_walletA | Show the Zearch credit balance this key spends from: available and held credits, plan, credit lots and when they expire. Optionally include recent ledger entries. Free. |
| get_pricingA | The public Zearch price list: credits per request type, plans and top-ups. Free; no API key needed. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| research_brief | A cited brief on a topic, built from Zearch deep research. |
| fact_check | Check a draft against sources with Zearch and report what is and isn’t supported. |
| compare | A side-by-side comparison with a citation in every cell. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| pricing | Credits per request type, plans and top-ups. |
| answer-view | Shows a checked answer with its citations and source passages. |
TDQS
Scored across 6 tools
The six tools mostly target distinct operations: research answers questions, verify checks third-party text, get_run/list_runs retrieve history, and get_wallet/get_pricing split private balance vs. public price list. The main wrinkle is that research folds six very different modes (scrape, crawl, compare, deep, reverse) into one tool with a mode argument, so an agent must read parameters rather than pick a tool. Wallet vs. pricing is a mild adjacency but the descriptions clearly separate them.
Four tools follow a clean verb_noun pattern (get_run, list_runs, get_wallet, get_pricing) with plural nouns on list/read endpoints. The two core tools, research and verify, are bare verbs with no object noun, which is a minor stylistic break but still readable and consistent with each other.
Six tools is well-scoped for a search-and-verification service: one entry point, one checker, two history readers, two billing readers. Nothing appears redundant or missing at the count level, and the heavy mode multiplexing is handled inside research rather than by exploding the tool list.
The lifecycle is largely covered: submit a job, verify text, fetch a single run, list history, and inspect balance/pricing. Minor gaps remain — no cancel or delete for queued or stale runs (notable given reverse runs can take minutes and hold 10 credits), and follow-ups are only expressible via the parent_id parameter on research rather than a dedicated operation.